Vidoc, an external security lab, replicated flagship vulnerabilities found by Mythos using other models like Claude Opus 4.6 or GP 5.4 with appropriate scaffolding.

Anthropic's Mythos LLM is so capable at computer security tasks that Anthropic did not release it publicly, instead granting access only to critical software makers.

Claude Mythos autonomously found and chained together several vulnerabilities in the Linux kernel, allowing an attacker to escalate from an ordinary user to complete control of the machine.

On SWEBench Pro, Claude Mythos achieved a 78% score, while Opus previously scored 53% and GPT 5.4 scored 57.7%.

The Mythos AI model is able to find zero-day vulnerabilities almost completely on its own with almost no guidance from a human.

Anthropic's testing found that Mythos Preview can identify and exploit zero-day vulnerabilities in every major operating system and web browser when directed by a user.